Research map / 3D vision / Human pose estimation
Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio
Xudong XU, Dejan Markovic, Jacob Sandakly, Todd Keebler, Steven Krenn, Alexander Richard
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add full body pose instead of no pose (ablation) | Ours · speech | SDR: 6.682 -> 9.580 | Improved |
| add full body pose instead of no pose (ablation) | Ours · non-speech | SDR: 2.518 -> 3.004 | Improved |
| use full body pose instead of head pose only (ablation) | Ours · speech | SDR: 9.264 -> 9.580 | Improved |
| use full body pose instead of head pose only (ablation) | Ours · non-speech | SDR: 2.848 -> 3.004 | Improved |
| add head pose to no-pose model (ablation) | Ours · speech | SDR: 6.682 -> 9.264 | Improved |
| increase head-mounted input mics from 1 to 7 (ablation) | Ours · non-speech | SDR: 0.848 -> 3.004 | Improved |
| increase head-mounted input mics from 1 to 7 (ablation) | Ours · speech | SDR: 8.259 -> 9.580 | Improved |
| increase input mics from 3 to 7 (ablation) | Ours · non-speech | SDR: 2.338 -> 3.004 | Improved |
| increase input mics from 3 to 7 (ablation) | Ours · speech | SDR: 9.526 -> 9.580 | Improved |
| replace l2 loss with shift-l2 loss (ablation) | Ours · non-speech | SDR: 2.557 -> 2.956 | Improved |
| replace multiscale STFT loss with shift-l2 + multiscale STFT (ablation) | Ours · speech | SDR: -5.077 -> 9.580 | Improved |
| add multiscale STFT to shift-l2 loss (ablation) | Ours · speech | amplitude error: 9.716 -> 7.059 | Improved |
Closest papers by meaning
- Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes (CVPR 2025 · similarity 0.88)
- 🎧MOSPA: Human Motion Generation Driven by Spatial Audio (NeurIPS 2025 · similarity 0.88)
- Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark (CVPR 2024 · similarity 0.86)
- MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations (NeurIPS 2025 · similarity 0.85)
- OmniAudio: Generating Spatial Audio from 360-Degree Video (ICML 2025 · similarity 0.85)
- Audible World Models: Spatially Aware Sound Generation for 3D Worlds (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
